Work

Systems we have shipped

Real problems, real constraints, real outcomes. Client names are anonymized unless we have explicit permission to share them.

Embedded EngineeringNational logistics distribution network · B2B operations

From email-driven ops to 90% platform adoption across a national distribution network

Challenge

Every operational process — approvals, resource requests, lifecycle events — ran through email threads. The system had fragmented modules with broken lifecycles, no automation, and no visibility. Teams spent more time coordinating than executing.

What we did

We joined the client's team to fix broken workflows, merge scattered modules into one system, and replace manual email steps with automated processes. We redesigned approvals and simplified user access permissions to match how the org actually works.

Outcomes

  • Platform adoption reached 90% — email-based operations eliminated
  • Resource management costs cut by 50%
  • Approvals and access permissions simplified across all modules
  • Automation introduced at every repeatable process touchpoint
Node.jsReactFastAPIPostgreSQLAWS
AI & Agentic SystemsMid-market finance team · Shared services

An AI agent that checks invoices and bills so people don't have to

Challenge

Every invoice and bill was checked by hand — matching amounts, catching duplicates, and flagging mismatches before payment. It was slow, easy to get wrong, and tied up the finance team for hours each day.

What we did

We built an AI agent that plugs into the invoice and bills modules and reads each document automatically. It matches the invoice to the right bill, checks the amounts, spots duplicates and errors, and only sends the unclear ones to a person. The routine checks now happen on their own.

Outcomes

  • Manual checking of invoices and bills almost fully removed
  • Payment errors and duplicate bills caught before money goes out
  • Finance team freed up to handle real exceptions, not routine matching
PythonLangChainOCRPgVectorLLM

Have a similar problem?

Tell us what you are building. We will tell you whether we can help and what that would look like.

Start a project